Agents · Benchmark profile

AutomationBench Private Set

The private AutomationBench enterprise-workflow set, kept separate from the public 600-task track and reference-only by default.

ReferencePrivate set, August 2026Active4 models

Data verified 13 Aug 2026 · Methodology 2.2.0

Benchmark score on AutomationBench Private Set

Leaderboard · 4 models

Gemini 3.7 Flash leads at 30.4%, followed by GPT-5.6 Terra (23.6%) and Gemini 3.6 Flash (17%).

Display onlyAgentsPrivate set, August 2026

#1Closed

Gemini 3.7 Flash

Google

gemini-3.7-flash

30.4%

Overall #6 · Context 1.05M tokens

#2Closed

GPT-5.6 Terra

OpenAI

gpt-5.6-terra

23.6%

Overall #9 · Context 1.05M tokens

#3Closed

Gemini 3.6 Flash

Google

gemini-3.6-flash

17%

Overall #20 · Context 1.05M tokens

ViewModelsColours

GoogleOpenAIAnthropic

Lumina

AutomationBench Private Set leaderboard

Accessible data for AutomationBench Private Set leaderboard
Model	Rank	Model ID	Provider	Score	Unit
Gemini 3.7 Flash	#1	gemini-3-7-flash	Google	30.4	percent
GPT-5.6 Terra	#2	gpt-5-6-terra	OpenAI	23.6	percent
Gemini 3.6 Flash	#3	gemini-3-6-flash	Google	17	percent
Claude Sonnet 5	#4	claude-sonnet-5	Anthropic	10.7	percent

Benchmark score table (4 models)

One best compatible score per canonical product · higher is better

AutomationBench Private Set leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Gemini 3.7 Flash gemini-3.7-flash	Google	closed	Reference only	30.4%
#2	GPT-5.6 Terra gpt-5.6-terra	OpenAI	closed	Reference only	23.6%
#3	Gemini 3.6 Flash gemini-3.6-flash	Google	closed	Reference only	17%
#4	Claude Sonnet 5 claude-sonnet-5	Anthropic	closed	Reference only	10.7%

The top of this snapshot is led by Gemini 3.7 Flash at 30.4%; third place is 13.4 points behind. The top-4 spread is 19.7 points.

Configuration-preserving evidencePublished source rows (4)Exact source labels, configurations, versions and dated observations. Same-snapshot canonical/configuration projections are shown once.

Every distinct dated source-published row for AutomationBench Private Set, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Gemini 3.7 Flash gemini-3-7-flash-medium	Gemini 3.7 Flash	30.4%	Private set, August 2026AutomationBench private set official public leaderboard	Reference only provider-reported	Google DeepMind permanent refresh source ↗Observed 2026-08-13 · checked 2026-08-13
GPT-5.6 Terra gpt-5-6-terra-max	GPT-5.6 Terra	23.6%	Private set, August 2026AutomationBench private set official public leaderboard	Reference only provider-reported	Google DeepMind permanent refresh source ↗Observed 2026-08-13 · checked 2026-08-13
Gemini 3.6 Flash gemini-3-6-flash-high	Gemini 3.6 Flash	17%	Private set, August 2026AutomationBench private set official public leaderboard	Reference only provider-reported	Google DeepMind permanent refresh source ↗Observed 2026-08-13 · checked 2026-08-13
Claude Sonnet 5 claude-sonnet-5-max	Claude Sonnet 5	10.7%	Private set, August 2026AutomationBench private set official public leaderboard	Reference only provider-reported	Google DeepMind permanent refresh source ↗Observed 2026-08-13 · checked 2026-08-13

Compare top models

Gemini 3.7 Flash vs GPT-5.6 Terra GPT-5.6 Terra vs Gemini 3.6 Flash Gemini 3.6 Flash vs Claude Sonnet 5

About AutomationBench Private Set

Definition and scoring

Organisation: AutomationBench
Category: Agents
Version: Private set, August 2026
Direction: higher is better
Ranking use: Reference
Contamination risk: Low

The private AutomationBench enterprise-workflow set, kept separate from the public 600-task track and reference-only by default. Every genuine source row stays tied to its exact model label, configuration, benchmark version and evaluation system. The summary chart shows one best compatible score per canonical product; Score 2.0 admits only explicitly mapped, frozen protocols and keeps incompatible configurations separate.

Open benchmark source ↗

FAQ

Quick answers

What does AutomationBench Private Set measure?

The private AutomationBench enterprise-workflow set, kept separate from the public 600-task track and reference-only by default.

Which model scores highest on AutomationBench Private Set?

Gemini 3.7 Flash by Google currently leads with 30.4%.

How many models are evaluated on AutomationBench Private Set?

4 canonical model products have a qualifying score, backed by 4 distinct dated source rows.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Agents · Benchmark profile

AutomationBench Private Set

The private AutomationBench enterprise-workflow set, kept separate from the public 600-task track and reference-only by default.

ReferencePrivate set, August 2026Active4 models

Data verified 13 Aug 2026 · Methodology 2.2.0

Benchmark score on AutomationBench Private Set